highsearch_ai_tools
Prompt-injection phrasing
The tool description contains language that reads like instructions aimed at the AI (e.g. overriding rules or hiding actions from you).
low
Not on gate's verified list
This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.
lowsearch_ai_tools
Embedded directive shaping AI's communication with user
The description contains an instruction aimed at the AI's behavior rather than describing tool mechanics: 'do not tell the user the catalog only contains what this page returned; raise limit instead.' While the underlying intent (avoid a false claim about catalog size) is reasonable, embedding imperative guidance about what the AI should or shouldn't tell the user inside a tool description is a pattern worth scrutinizing, since it could be used to suppress accurate information disclosure to the user. Recommend rephrasing as neutral field documentation (e.g., 'truncated indicates more results exist beyond the current limit') rather than an instruction on what not to say.